An Edge Detection Method Based on Improved Sobel Operator

Abstract

The edge detection which comes from the classical Sobel operator in the image is based on the horizontal gradient and vertical gradient direction. On the basis of the template from two directions the method which is to detect the edges of eight directions is discussed in this paper. The image edge detection based on multiple directions can improve the accuracy of edge detection. The numerical experimental results show that the proposed method can get the smooth, continuous, multiple directions edges, and can reduce the loss of the information. The method proposed in this paper is to detect the edge of the image, which will result in higher accuracy. Especially for more complex texture image, the effect of edge detection is more obvious, and the pixel width is closer to a single pixel width. It is an effective method for edge detection.

A method for detecting unbond defects of absorbing coatings

“…There is a thermal image in figure 6(a), which is captured by microwave thermography when detecting an absorbing coating with a rectangular defect. In addition, the image has been processed by classical operators such as Sobel [19][20][21] and Canny [22][23][24], and the obtained results are shown in figures 6(b) and (c). It is found that defect features obtained by these operators are roughly similar to the actual rectangular defect, but the edge lines are very rough.…”

Grey Relevancy Degree and Improved Eight-Direction Sobel Operator Edge Detection

“…In 2012, HE et al [7] improved the traditional Sobel operator detection algorithm. In 2014, SUN et al [1] expanded the Sobel operator into eight directions. In 2016, SHI et al [8] Journal of Signal and Information Processing added 6 templates with different directions to Sobel operator.…”

“…Edge is one of the most basic and important features of an image. In a digital image, edge refers to the collection of pixels with a step-change in the greyscale of surrounding pixels, which exists in the target and background, target and target, region and region, elements and elements [1]. So, the essence of image edge detection is to detect the change of position feature in the image.…”

An Improved Algorithm of Parameter Kernel Cutting Based on Complex Fusion Image

“…The edge detection is realized by differentiating the gray value of the image with differential operator. Sobel operator in [7] and Canny operator in [8] are commonly used differential operators for image edge detection, which are widely used in image edge extraction. In most cases, image segmentation and image edge extraction are achieved via converting a color image into a grayscale image.…”